OpenAI.Net.Client 1.0.13

<img src="https://raw.githubusercontent.com/jodendaal/OpenAI.Net/main/src/OpenAI.Net/OpenAILogo.svg" alt="OpenAI" width="300"/>

OpenAI.Net

OpenAI library for .NET

C# .NET library for use with the OpenAI API.

This is community-maintained library.

This library supports .net core 6.0 and above.

Getting started

Install package Nuget package

Install-Package OpenAI.Net.Client

Register services using the provided extension methods

services.AddOpenAIServices(options => {
    options.ApiKey = builder.Configuration["OpenAI:ApiKey"];
});

N.B We recommend using environment variables, configuration files or secret file for storing the API key securely. See here for further details.

Example Usage

You can view examples of a console, web application and Blazor app using the streaming API here.

You can also have a look at the Integration Tests for usage examples here.

Simple console app usage below.

using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
using OpenAI.Net;

namespace ConsoleApp
{
    internal class Program
    {
        static async void Main(string[] args)
        {
            using var host = Host.CreateDefaultBuilder(args)
            .ConfigureServices((builder, services) =>
            {
                services.AddOpenAIServices(options => {
                    options.ApiKey = builder.Configuration["OpenAI:ApiKey"];
                });
            })
            .Build();

            var openAi = host.Services.GetService<IOpenAIService>();
            var response = await openAi.TextCompletion.Get("How long until we reach mars?");

            if (response.IsSuccess)
            {
                foreach(var result in response.Result.Choices)
                {
                    Console.WriteLine(result.Text);
                }
            }
            else
            {
                Console.WriteLine($"{response.ErrorMessage}");
            }
        }
    }
}

Configuring Http Client Options

The registration extension allows for configuration of the http client via the IHttpClientBuilder interface.

This allows for adding a Polly retry policy for example. See example here.

services.AddOpenAIServices(options => {
    options.ApiKey = builder.Configuration["OpenAI:ApiKey"];
}, 
(httpClientOptions) => {
    httpClientOptions.AddPolicyHandler(GetRetryPolicy());
});

static IAsyncPolicy<HttpResponseMessage> GetRetryPolicy()
{
    return HttpPolicyExtensions
        .HandleTransientHttpError()
        .WaitAndRetryAsync(3, retryAttempt => TimeSpan.FromSeconds(Math.Pow(2,
                                                                    retryAttempt)));
}

Supported API's

Full support of all current API's

• Models

  • List Models
  • Retrieve model

• Completions

  • Create completion
  • Create completion with streaming

• Edits

  • Create edit

• Images

  • Create image
  • Create image edit
  • Create image variation

• Embeddings

  • Create embeddings

• Files

  • List files
  • Upload file
  • Delete file
  • Retrieve file
  • Retrieve file content

• Fine-tunes

  • Create fine-tune
  • List fine-tunes
  • Retrieve fine-tune
  • Cancel fine-tune
  • List fine-tune events
  • Delete fine-tune model

• Moderations

  • Create moderation

Testing

This project has 100% code coverage with Unit tests and 100% pass rate with Stryker mutation testing.

See latest Stryker report here.

We also have Integration tests foreach service.

This should provide confidence in the library going forwards.

Examples

Completion

var response = await service.TextCompletion.Get("Say this is a test",(o) => {
                o.MaxTokens = 1024;
                o.BestOf = 2;
            });

Completion Stream

await foreach(var response in service.TextCompletion.GetStream("Say this is a test"))
{
    Console.WriteLine(response?.Result?.Choices[0].Text);
}

Completion with array input

var prompts = new List<string>()
{
    "Say this is a test",
    "Say this is not a test"
};

var response = await service.TextCompletion.Get(prompts,(o) => {
                o.MaxTokens = 1024;
                o.BestOf = 2;
            });

Text Edit

var response = await service.TextEdit.Get("Fix the spelling mistakes", "What day of the wek is it?", (o =>{
    o.TopP = 0.1;
    o.Temperature = 100;
}));

Image Edit

Using file paths

var response = await service.Images.Edit("A cute baby sea otter", @"Images\BabyCat.png", @"Images\Mask.png", o => {
    o.N = 99;
});

Using file bytes

var response = await service.Images.Edit("A cute baby sea otter",File.ReadAllBytes(@"Images\BabyCat.png"), File.ReadAllBytes(@"Images\BabyCat.png"), o => {
    o.N = 99;
});

Image Generate

var response = await service.Images.Generate("A cute baby sea otter",2, "1024x1024");

Image Variation

Using file paths

var response = await service.Images.Variation(@"Images\BabyCat.png", o => {
    o.N = 2;
    o.Size = "1024x1024";
});

Using file bytes

 var response = await service.Images.Variation(File.ReadAllBytes(@"Images\BabyCat.png"), o => {
                o.N = 2;
                o.Size = "1024x1024";
});

Fine Tune Create

var response = await service.FineTune.Create("myfile.jsonl", o => {
    o.BatchSize = 1;
});

Fine Tune Get All

var response = await service.FineTune.Get();

Fine Tune Get By Id

var response = await service.FineTune.Get("fineTuneId");

Fine Tune Get Events

var response = await service.FineTune.GetEvents("fineTuneId");

Fine Tune Delete

var response = await service.FineTune.Delete("modelId");

Fine Tune Cancel

var response = await service.FineTune.Cancel("fineTuneId");

File Upload

Using file path

var response = await service.Files.Upload(@"Images\BabyCat.png");

Using file bytes

var response = await service.Files.Upload(bytes, "mymodel.jsonl");

File Get Content

 var response = await service.Files.GetContent("fileId");

File Get File Detail

var response = await service.Files.Get("fileId");

File Get File All

var response = await service.Files.Get();

File Delete

var response = await service.Files.Delete("1");

Emdeddings Create

var response = await service.Embeddings.Create("The food was delicious and the waiter...", "text-embedding-ada-002", "test");

Models Get All

var response = await service.Models.Get();

Models Get By Id

var response = await service.Models.Get("babbage");

Moderation Create

var response = await service.Moderation.Create("input text", "test");

Contributions

Contributions are welcome.

Minimum requirements for any PR's.

• MUST include Unit tests and maintain 100% coverage.

• MUST pass Stryker mutation testing with 100%

• SHOULD have integration tests